Image transform bootstrapping and its applications to semantic scene classification

The performance of an exemplar-based scene classification system depends largely on the size and quality of its set of training exemplars, which can be limited in practice. In addition, in nontrivial data sets, variations in scene content as well as distracting regions may exist in many testing images to prohibit good matches with the exemplars. Various boosting schemes have been proposed in machine learning, focusing on the feature space. We introduce the novel concept of image-transform bootstrapping using transforms in the image space to address such issues. In particular, three major schemes are described for exploiting this concept to augment training, testing, and both. We have successfully applied it to three applications of increasing difficulty: sunset detection, outdoor scene classification, and automatic image orientation detection. It is shown that appropriate transforms and meta-classification methods can be selected to boost performance according to the domain of the problem and the features/classifier used.

[1]  Anil K. Jain,et al.  Content-based hierarchical classification of vacation images , 1999, Proceedings IEEE International Conference on Multimedia Computing and Systems.

[2]  W. Eric L. Grimson,et al.  Configuration based scene classification and image indexing , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Nicu Sebe,et al.  Learning Bayesian network classifiers for facial expression recognition both labeled and unlabeled data , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[4]  Francis K. H. Quek,et al.  Attribute bagging: improving accuracy of classifier ensembles by using random feature subsets , 2003, Pattern Recognit..

[5]  Takeo Kanade,et al.  Rotation Invariant Neural Network-Based Face Detection , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[6]  John R. Smith,et al.  Image Classification and Querying Using Composite Region Templates , 1999, Comput. Vis. Image Underst..

[7]  Tomaso A. Poggio,et al.  Example-Based Learning for View-Based Human Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Tong Zhang,et al.  The Value of Unlabeled Data for Classification Problems , 2000, ICML 2000.

[9]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[10]  Anil K. Jain,et al.  Automatic image orientation detection , 2002, IEEE Trans. Image Process..

[11]  Marcel Worring,et al.  Content-Based Image Retrieval at the End of the Early Years , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Robert P. W. Duin,et al.  The combining classifier: to train or not to train? , 2002, Object recognition supported by user interaction for service robots.

[14]  Stephen D. Bay.  Combining Nearest Neighbor Classifiers Through Multiple Feature Subsets , 1998, ICML.

[15]  Yongmei Wang,et al.  Content-based image orientation detection with support vector machines , 2001, Proceedings IEEE Workshop on Content-Based Access of Image and Video Libraries (CBAIVL 2001).

[17]  Robert P. W. Duin,et al.  Bagging for linear classifiers , 1998, Pattern Recognit..

[18]  Jitendra Malik,et al.  Blobworld: Image Segmentation Using Expectation-Maximization and Its Application to Image Querying , 2002, IEEE Trans. Pattern Anal. Mach. Intell..